scispace - formally typeset
Search or ask a question
Author

Raj Jena

Bio: Raj Jena is an academic researcher from University of Cambridge. The author has contributed to research in topics: Medicine & Radiation therapy. The author has an hindex of 16, co-authored 32 publications receiving 3736 citations. Previous affiliations of Raj Jena include Cambridge University Hospitals NHS Foundation Trust.

Papers
More filters
Journal ArticleDOI
TL;DR: The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) as mentioned in this paper was organized in conjunction with the MICCAI 2012 and 2013 conferences, and twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low and high grade glioma patients.
Abstract: In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

3,699 citations

Book ChapterDOI
01 Oct 2012
TL;DR: The discriminative approach is based on decision forests using context-aware spatial features, and integrates a generative model of tissue appearance, by using the probabilities obtained by tissue-specific Gaussian mixture models as additional input for the forest.
Abstract: We present a method for automatic segmentation of high-grade gliomas and their subregions from multi-channel MR images. Besides segmenting the gross tumor, we also differentiate between active cells, necrotic core, and edema. Our discriminative approach is based on decision forests using context-aware spatial features, and integrates a generative model of tissue appearance, by using the probabilities obtained by tissue-specific Gaussian mixture models as additional input for the forest. Our method classifies the individual tissue types simultaneously, which has the potential to simplify the classification task. The approach is computationally efficient and of low model complexity. The validation is performed on a labeled database of 40 multi-channel MR images, including DTI. We assess the effects of using DTI, and varying the amount of training data. Our segmentation results are highly accurate, and compare favorably to the state of the art.

275 citations

Journal ArticleDOI
TL;DR: The inherent invasiveness of malignant cells is a major determinant of the poor prognosis of cerebral gliomas and diffusion tissue signatures may be a useful method of assessing occult white matter infiltration.
Abstract: The inherent invasiveness of malignant cells is a major determinant of the poor prognosis of cerebral gliomas. Diffusion tensor MRI (DTI) can identify white matter abnormalities in gliomas that are not seen on conventional imaging. By breaking down DTI into its isotropic (p) and anisotropic (q) components, we can determine tissue diffusion "signatures". In this study we have characterised these abnormalities in peritumoural white matter tracts. Thirty-five patients with cerebral gliomas and seven normal volunteers were imaged with DTI and T2-weighted sequences at 3 T. Displaced, infiltrated and disrupted white matter tracts were identified using fractional anisotropy (FA) maps and directionally encoded colour maps and characterised using tissue signatures. The diffusion tissue signatures were normal in ROIs where the white matter was displaced. Infiltrated white matter was characterised by an increase in the isotropic component of the tensor (p) and a less marked reduction of the anisotropic component (q). In disrupted white matter tracts, there was a marked reduction in q and increase in p. The direction of water diffusion was grossly abnormal in these cases. Diffusion tissue signatures may be a useful method of assessing occult white matter infiltration.

116 citations

01 Oct 2012
TL;DR: This submission to the Brain Tumor Segmentation Challenge (BraTS) at MICCAI 2012 is described, which is based on the method for tissue-specic segmentation of high-grade brain tumors, and is able to capture the context information for each data point.
Abstract: We describe our submission to the Brain Tumor Segmenta- tion Challenge (BraTS) at MICCAI 2012, which is based on our method for tissue-specic segmentation of high-grade brain tumors (3). The main idea is to cast the segmentation as a classication task, and use the discriminative power of context information. We realize this idea by equipping a classication forest (CF) with spatially non-local features to represent the data, and by providing the CF with initial probability estimates for the single tissue classes as additional input (along-side the MRI channels). The initial probabilities are patient-specic, and com- puted at test time based on a learned model of intensity. Through the combination of the initial probabilities and the non-local features, our approach is able to capture the context information for each data point. Our method is fully automatic, with segmentation run times in the range of 1-2 minutes per patient. We evaluate the submission by cross- validation on the real and synthetic, high- and low-grade tumor BraTS data sets.

88 citations

Journal ArticleDOI
TL;DR: ABT-888 has the clinical potential to enhance the current standard treatment for GBM, in combination with conventional chemo-radiotherapy and the use of PARP inhibitors might be clinically significant in those patients whose tumour is MGMT-unmethylated and currently derive less benefit from TMZ.
Abstract: The cytotoxicity of radiotherapy and chemotherapy can be enhanced by modulating DNA repair. PARP is a family of enzymes required for an efficient base-excision repair of DNA single-strand breaks and inhibition of PARP can prevent the repair of these lesions. The current study investigates the trimodal combination of ABT-888, a potent inhibitor of PARP1-2, ionizing radiation and temozolomide(TMZ)-based chemotherapy in glioblastoma (GBM) cells. Four human GBM cell lines were treated for 5 h with 5 μM ABT-888 before being exposed to X-rays concurrently with TMZ at doses of 5 or 10 μM for 2 h. ABT-888′s PARP inhibition was measured using immunodetection of poly(ADP-ribose) (pADPr). Cell survival and the different cell death pathways were examined via clonogenic assay and morphological characterization of the cell and cell nucleus. Combining ABT-888 with radiation yielded enhanced cell killing in all four cell lines, as demonstrated by a sensitizer enhancement ratio at 50% survival (SER50) ranging between 1.12 and 1.37. Radio- and chemo-sensitization was further enhanced when ABT-888 was combined with both X-rays and TMZ in the O6-methylguanine-DNA-methyltransferase (MGMT)-methylated cell lines with a SER50 up to 1.44. This effect was also measured in one of the MGMT-unmethylated cell lines with a SER50 value of 1.30. Apoptosis induction by ABT-888, TMZ and X-rays was also considered and the effect of ABT-888 on the number of apoptotic cells was noticeable at later time points. In addition, this work showed that ABT-888 mediated sensitization is replication dependent, thus demonstrating that this effect might be more pronounced in tumour cells in which endogenous replication lesions are present in a larger proportion than in normal cells. This study suggests that ABT-888 has the clinical potential to enhance the current standard treatment for GBM, in combination with conventional chemo-radiotherapy. Interestingly, our results suggest that the use of PARP inhibitors might be clinically significant in those patients whose tumour is MGMT-unmethylated and currently derive less benefit from TMZ.

86 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: Two specific computer-aided detection problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification are studied, achieving the state-of-the-art performance on the mediastinal LN detection, and the first five-fold cross-validation classification results are reported.
Abstract: Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

4,249 citations

Journal ArticleDOI
TL;DR: The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) as mentioned in this paper was organized in conjunction with the MICCAI 2012 and 2013 conferences, and twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low and high grade glioma patients.
Abstract: In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

3,699 citations

Journal ArticleDOI
TL;DR: An efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data, and improves on the state-of-the‐art for all three applications.

2,842 citations

Journal ArticleDOI
TL;DR: A fast and accurate fully automatic method for brain tumor segmentation which is competitive both in terms of accuracy and speed compared to the state of the art, and introduces a novel cascaded architecture that allows the system to more accurately model local label dependencies.

2,538 citations

Journal ArticleDOI
TL;DR: nnU-Net as mentioned in this paper is a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task.
Abstract: Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

2,040 citations